Sequential Designs for Complex Computer Experiments with an Application to a Nuclear Fusion Model

복잡한 전산실험을 위한 축차적 계획법과 핵 융합모형에의 응용

  • Jeong Soo Park (Department of Statistics, Chonnam National University, 300 Yongbong-dong, Kwangju 500-747, Korea)
  • Published : 1994.09.01

Abstract

Data-adaptive sequential suboptimal designs for very complex computer simulation codes are considered based on a spatial prediction model. These designs are constructed for two simulators of the computational nuclear fusion devices model. The difficulty of constructing the optimal designs due to the irregular design region, and its alternatives are also discussed with some computational algorithms for obtaining the designs.

매우 복잡한 컴퓨터 시뮬레이션 실험을 이용한 제반 연구의 효용성을 높이기 위하여 공간적 예측모형에 기초한, 자료참조의 축차적 부최적 실험계획법을 고려하였다. 이 실험계획법들은 실제로 핵융합기기의 반응모형 시뮬레이터에 적용되었으며, 적용상의 효과적 방법과 경험이 기술되었다. 또한 비정상적으로 주어진 실험영역과 최적기준의 계산상의 복잡함으로 인하여 실제의 최적 실험계획을 구축하는데 어려움이 많았고, 따라서 이에 대한 대안들이 컴퓨터 알고리즘과 함께 제안되었다.

Keywords

References

  1. Technical Report 34, Department of Statistics, University of Illinois Updatable Computations for Best Linear Unbiased Predictors Cox,D.;Chang,Y.
  2. Statistics for Spatial Data Cressie,N.
  3. Journal of the American Statistical Association v.86 Bayesian Prediction of Deterministic Functions, With Applications to the Design and Analysis of Computer Experiments Currin,C.;Mitchell,T.;Morris,M.;Ylvisaker,D.
  4. Journal of Institute of Mathematics and Apllications v.9 Quasi-Newton methods for unconstraint optimization Gill,P.;Murray,W.
  5. Journal of Statistical Planning and Inferences v.26 Minimax and Maximin Distance Designs Johnson,M.E.;Moore,L.M.;Ylvisaker,D.
  6. Nuclear Fusion v.25 Global Energy Confinement Scaling for Neutral-Beam-Heated Tokamak Kaye,S.M.;Goldston,G.C.
  7. Technometrics v.21 A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code McKay,M.D.;Bechman,R.J.;Conover,W.J.
  8. NAG Fortran Library Manual, Mark Ⅱ v.3 Numerical Analysis Group
  9. Journal of Royal Statistical Society, Ser. B A Central Limit Theorem for Latin Hypercube Sampling Owen,A.B.
  10. Unpublished Ph.D. thesis, University of Illinois at Urbana-Champaign Tuning Complex Computer Codes to Data and Optimal Designs Park,J.
  11. Efficient computation and unimodelity of the likelihood in a spatial linear model Park,J.;Cho,W.
  12. Spatial Statistics Ripley,B.
  13. Statistical Decision Theory and Related Topics Ⅳ v.2 Spatial Designs Sacks,J.;Schiller,S.B.;S.S.Gupta(eds.);J.O.Berger(eds.)
  14. Technometrics v.31 Designs for Computer Experiments Sacks,J.;Schiller,S.B.;Welch,W.J.
  15. Statistical Science v.4 Design and analysis of computer experiments (with discussion) Sacks,J.;Welch,W.;Mitchell,T.;Wynn,H.
  16. Journal of Applied Statistics v.14 Maximum Entropy Sampling Shewry,M.;Wynn,H.
  17. Korean Journal of Applied Statistics v.7 Design and analysis of computer experiments, with an application to quality improvements Sim,J.W.;Park,J.S.;Bai,J.S.
  18. Computer Physics Communications v.49 BALDUR: A One-Dimensional Plasma Transport Code Singer,C.E.;Post,D.E.;Mikkelsen,D.R.;Redi,M.H.(et al.)
  19. Technometrics v.29 Large Sample Properties of Simulations using Latin Hypercube Sampling Stein,M.
  20. Journal of Quality Technology v.22 Computer Experiments for Quality Control by Parameter Design Welch,W.J.;Yu,T.K.;Kang,S.M.;Sacks,J.